引導式測驗 · 中等 等級
生成對抗網路測驗
回顧生成器和判別器的角色、原始 GAN 輸入、對抗性回饋、模式崩潰、歷史起源、均衡和調節。
問題 1 的 8
GAN 中的兩個競爭網路是什麼?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- GAN 中的兩個競爭網路是什麼?
- 編碼器和解碼器
- 一個讀者和一個作家
- 兩個相同的副本始終一致
- 生成贗品的生成器與判斷贗品的鑑別器
- In the original unconditional GAN formulation, what input does the generator transform into a sample?
- A guaranteed copy of a finished real image
- Sampled latent noise
- The discriminator's parameter file
- A fixed human-written answer key
- What adversarial learning signal can reach a GAN generator through its discriminator?
- Gradients of the generator objective with respect to its parameters
- A rule that every generated image is correct
- A prohibition against all conditional image inputs
- A copy of every discriminator weight as the output image
- 什麼是 GAN 中的「模式崩潰」?
- 鑑別器刪除所有數據
- 網路記憶體不足
- 生成器僅產生少量重複輸出,而不是多樣性
- 影像解析度自動加倍
- Which researchers introduced the GAN framework in the 2014 paper?
- Alan Turing alone in 1950
- 伊恩·古德費洛和同事
- Geoffrey Hinton alone in 2006
- Yann LeCun alone in 1998
- How can a conventional feed-forward GAN generator produce one sample after training?
- By requiring exactly a thousand discriminator updates at inference
- By retrieving an unchanged target image in every case
- Without evaluating any learned computation
- With one forward evaluation of the generator
- At the ideal original GAN equilibrium where generated and real distributions match, what probability does the optimal discriminator assign to an example being real?
- Zero for every example
- One for every example
- 二分之一
- A probability greater than one
- In the conditional GAN formulation, where can a class label or other condition be supplied?
- To both the generator and the discriminator
- Only to an unrelated output filename
- To neither network by definition
- Only after all training and generation have finished